Sr. ML Engineer (Network Anomaly)
Job Description
- Experience or domain knowledge in network security, network protocols, or cybersecurity.
- Experience with modern GenAI stacks (e.g., LLM Agents, RAG, NLP).
- Experience with Lakehouse Open Table Formats (e.g., Apache Iceberg, Delta Lake, Hudi).
- Experience with Infrastructure as Code (e.g., Terraform, AWS Cloudformation, AWS CDK).
- Fluent in English.
- Research and develop ML models for network anomaly detection.
- Design and optimize data pipelines and ML workflows.
- Engineer and validate detection metrics and features.
- Collaborate with network domain experts to improve models.
- Own full lifecycle of detection models (prototyping, deployment, monitoring).
- BS or MS degree in Computer Science, Statistics, Mathematics, or related field.
- Solid understanding of unsupervised ML, statistical models, and time-series analysis for anomaly detection.
- Proficiency in Python and SQL for data-intensive applications.
- Proven experience with distributed data processing frameworks (e.g., Spark, Flink) and workflow orchestration tools (e.g., Apache Airflow, Prefect).
- Strong experience in MLOps practices, including CI/CD, automated testing, containerization (e.g., Docker, Kubernetes), and service monitoring (e.g., Grafana, Kibana).
- Hands-on experience developing solutions on at least one major cloud platform (AWS, Azure, or GCP).
- 3+ years of hands-on experience building and deploying machine learning models into production environments.
- Strong problem-solving skills, a proactive attitude, and ability to drive projects independently.
Overview
We are looking for talented Sr. ML Engineer to help us to study, design and implement anomaly detection in XDR for Networks for Trend Vision One™. You will collaborate with network domain experts to generate a lot of valuable network anomaly detection to customers so that they are protected by proactive network security information.
Responsibilities
1. Research and develop state-of-the-art machine learning models to detect and classify anomalies within large-scale, high-velocity network data.
2. Design, implement, and optimize robust, end-to-end data pipelines and ML workflows for batch/real-time anomaly detection.
3. Engineer and validate key detection metrics and features that provide precise and actionable insights.
4. Collaborate with network domain experts to continuously improve model performance, reduce false positives, and enhance detection capabilities.
5. Own the full lifecycle of detection models, including prototyping, testing, deployment, monitoring, and iteration.
Essential Requirements
1. BS or MS degree in Computer Science, Statistics, Mathematics, or a related technical field.
2. Solid understanding and applied experience in machine learning, particularly in unsupervised learning (e.g., clustering, density estimation), statistical models, and time-series analysis for anomaly detection.
3. Proficiency in Python and SQL for building data-intensive applications.
4. Proven experience with distributed data processing frameworks (e.g., Spark, Flink) and workflow orchestration tools (e.g., Apache Airflow, Prefect).
5. Strong experience in MLOps practices, including CI/CD, automated testing, containerization (e.g., Docker, Kubernetes), and service monitoring (e.g., Grafana, Kibana).
6. Hands-on experience developing solutions on at least one major cloud platform (AWS, Azure, or GCP).
7. 3+ years of hands-on experience building and deploying machine learning models into production environments.
8. Strong problem-solving skills, a proactive attitude, and the ability to drive projects independently.
Nice-to-have as a plus
1. Experience or domain knowledge in network security, network protocols, or cybersecurity.
2. Experience with modern GenAI stacks (e.g., LLM Agents, RAG, NLP).
3. Experience with Lakehouse Open Table Formats (e.g., Apache Iceberg, Delta Lake, Hudi).
4. Experience with Infrastructure as Code (e.g., Terraform, AWS Cloudformation, AWS CDK).
5. Fluent in English.
